Summary: A Neural Network Approach to the
Consistent Labeling Problem
Jiansheng Feng \Lambda Wenjing Tao Hans Burkhardt
Technische Informatik I
Technische Universit¨at Hamburg­Harburg
2100 Hamburg 90, Germany
Abstract--- This paper presents a method to
solve the consistent labeling problem, especially
the high­order constraint case, by the Hopfield
network. A agitating method is also proposed to
tackle the problem of local minima. Some experi­
ments concerning line drawing labeling are demon­
strated.
I. Introduction
The consistent labeling problem (CLP) proposed by
Haralick and Shapiro [1] and Ullmann [2] concerns a gen­
eral technique for solving a class of problems in artificial
intelligence, such as subgraph isomorphism and homomor­
phism [3], [4], graph coloring [4], school­timetabling [2],
theorem proving [1], puzzle solving [1], [2], scene labeling

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

Collections: Computer Technologies and Information Sciences